17 neural-network positions at Monash University

PhD Scholarship in Philosophy

Tsuchiya, and Dr Thomas Andrillon. The Dreamscape Project aims to discover the neural basis of dreaming. Building on the world’s largest database of sleep electroencephalograms (EEG) and associated dream

Safe Neuro-symbolic Automated Decision Making with Mathematical Optimisation

[1,2,3,4,5,6] have shown that the unknown transition models can be accurately approximated as neuro-symbolic (deep) neural networks which then can be compiled into mathematical optimisation models (e.g., MILP

Brain network mechanisms underlying anaesthetic-induced loss of consciousness

This project focuses on brain network mechanisms underlying anaesthetic-induced loss of consciousness through the application of simultaneous EEG/MEG and neural inference and network analysis

End-to-End Prediction and Optimisation for Neuro-Symbolic Artificial Intelligence

traditional optimisation methods and modern deep learning techniques. Mixed integer linear programming is a successful discrete optimisation methodology but it is incompatible with deep neural networks, which

Context-Dependent Neural Machine Translation

context for monologue and multi-party bilingual dialogue translation [1,2, 3], capitalizing on the flexibility and expressive power of deep learning and neural networks. In this project, we will push the

Measures of Simplicity in Optimisation-based Machine Learning

can be used to learn simple models (e.g., decision trees [6], decision graphs [4, 5], etc.) or improve more complex models (e.g., neural networks [2]). Recent advancements in mathematical optimisation

Deep learning from less human supervision

models (eg auto-encoders and generative adversarial networks) and reinforcement/imitation learning algorithms for Markov Decision Processes. The application areas are different problems in text processing

Towards adversarially robust deep models

Deep Neural Networks have shown remarkable performance across a wide range of computer vision tasks. They are however vulnerable to carefully crafted, human imperceptible perturbations, which once

Advanced statistical inference and machine learning for neural modelling, monitoring and imaging

variables such as network connection strengths between neural population networks underlying brain activity. We work with different physiological data modalities such as intracranial and scalp

Characterising Model Complexity for Data-driven Scientific Discovery

to new unseen data. Interest in this are has recently resurged due to the discovery of phenomena such as "double descent", and the use of new model types such as deep neural networks, which challenge